Related papers: Figure It Out: Improve the Frontier of Reasoning w…

Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful…

Chain-of-Thought (CoT) reasoning has been widely adopted to enhance Large Language Models (LLMs) by decomposing complex tasks into simpler, sequential subtasks. However, extending CoT to vision-language reasoning tasks remains challenging,…

Large language models (LLMs) excel at many supervised tasks but often struggle with structured reasoning in unfamiliar settings. This discrepancy suggests that standard fine-tuning pipelines may instill narrow, domain-specific heuristics…

Grounding natural language in images, such as localizing "the black dog on the left of the tree", is one of the core problems in artificial intelligence, as it needs to comprehend the fine-grained and compositional language space. However,…

We present a lightweight yet effective pipeline for training vision-language models to solve math problems by rendering LaTeX encoded equations into images and pairing them with structured chain-of-thought prompts. This simple…

Visual thinking plays an important role in scientific reasoning. Based on the research in automating diverse reasoning tasks about dynamical systems, nonlinear controllers, kinematic mechanisms, and fluid motion, we have identified a style…

Humans often use visual aids, for example diagrams or sketches, when solving complex problems. Training multimodal models to do the same, known as Visual Chain of Thought (Visual CoT), is challenging due to: (1) poor off-the-shelf visual…

Recent work on reinforcement learning with verifiable rewards (RLVR) has shown that large language models (LLMs) can be substantially improved using outcome-level verification signals, such as unit tests for code or exact-match checks for…

Multi-modal large language models (MLLMs) exhibit strong general-purpose capabilities, yet still struggle on Fine-Grained Visual Classification (FGVC), a core perception task that requires subtle visual discrimination and is crucial for…

Visual question answering requires high-order reasoning about an image, which is a fundamental capability needed by machine systems to follow complex directives. Recently, modular networks have been shown to be an effective framework for…

Recent progress in Multi-modal Large Language Models (MLLMs) has enabled step-by-step multi-modal mathematical reasoning by performing visual operations based on the textual instructions. A promising approach uses code as an intermediate…

In-context imitation learning enables robots to adapt to new tasks from a small number of demonstrations without additional training. However, existing approaches typically condition only on state-action trajectories and lack explicit…

General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-thought prompting, have achieved considerable success on…

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find…

Large language models have achieved near-expert performance in structured reasoning domains like mathematics and programming, yet their ability to perform compositional multi-hop reasoning in specialized scientific fields remains limited.…

In knowledge-intensive tasks, especially in high-stakes domains like medicine and law, it is critical not only to retrieve relevant information but also to provide causal reasoning and explainability. Large language models (LLMs) have…

While chains-of-thought (CoT) have advanced complex reasoning in multimodal large language models (MLLMs), existing methods remain confined to text or static visual domains, often faltering in dynamic spatial reasoning tasks. To bridge this…

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

Recent works have made notable advancements in enhancing unified models for text-to-image generation through the Chain-of-Thought (CoT). However, these reasoning methods separate the processes of understanding and generation, which limits…

While vision-language models (VLMs) have exhibited multi-turn visual reasoning capabilities, their reasoning trajectories remain relatively shallow and are dominated by a text-centric paradigm, limiting their applicability to complex visual…